buzzwords 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 28d272a397f727d163056668a9b1998d4c79835c
+  data.tar.gz: 473704a343deca9793d00414f4bebe81b24cfd95
+SHA512:
+  metadata.gz: 79103b449a23f0c2888fead2a6c78ead5bc4259f42463e38ce09d2462e52698a5cd6b29dcb74b956c51b5b18b44f403410e3d8610ef6216cd574479efa312fb0
+  data.tar.gz: 6a0383662d3a023780d9684c7f305394f8d8e09cd9f3d7c85bc66e7c36408678ecb7738e80e0431c94932a972463e52bc3490b3e63a80fd21cc1587aa89d4045

data/lib/buzzwords.rb

@@ -0,0 +1,80 @@
+require 'mechanize'
+
+require_relative 'buzzwords/ny_times.rb'
+require_relative 'buzzwords/washington_post.rb'
+require_relative 'buzzwords/cnn.rb'
+require_relative 'buzzwords/reuters.rb'
+require_relative 'buzzwords/stopwords.rb'
+
+class Buzzwords
+  MECH = Mechanize.new
+
+  @aggregate_headlines = []
+  @word_occurrences = Hash.new(0)
+  @top_words = nil
+
+  class << self
+    attr_accessor :aggregate_headlines, :word_occurrences, :top_words
+  end
+
+  def self.generate_buzz
+    display_loading
+    retrieve_nytimes_headlines
+    retrieve_wapo_headlines
+    retrieve_cnn_headlines
+    retrieve_reuters_headlines
+    filter_stopwords
+    count_word_occurrences
+    determine_top_words
+    display_top_words
+  end
+
+  def self.display_loading
+    puts "Loading current buzzwords..."
+  end
+
+  def self.retrieve_nytimes_headlines
+    self.aggregate_headlines += parse_headlines(NYTimes.new.headlines)
+  end
+
+  def self.retrieve_wapo_headlines
+    self.aggregate_headlines += parse_headlines(WashingtonPost.new.headlines)
+  end
+
+  def self.retrieve_cnn_headlines
+    self.aggregate_headlines += parse_headlines(CNN.new.headlines)
+  end
+
+  def self.retrieve_reuters_headlines
+    self.aggregate_headlines += parse_headlines(Reuters.new.headlines)
+  end
+
+  def self.parse_headlines(data)
+    data.map(&:split).flatten.map do |word|
+      word.delete('/\A[\W]/').delete('/[\W]\z/').gsub(/\'s/, '')
+    end
+  end
+
+  def self.filter_stopwords
+    self.aggregate_headlines = aggregate_headlines.select do |word|
+      Stopwords.valid?(word)
+    end
+  end
+
+  def self.count_word_occurrences
+    aggregate_headlines.each do |word|
+      word_occurrences[word] += 1
+    end
+  end
+
+  def self.determine_top_words
+    self.top_words = word_occurrences.sort_by { |k, v| v }.reverse.take(20)
+                    .reject{ |word| word.last < 3 }
+                    .map { |word| word.first }
+  end
+
+  def self.display_top_words
+    puts "Today's top buzzwords are: "
+    puts top_words.map { |word| " - #{word}" }
+  end
+end

data/lib/buzzwords/cnn.rb

@@ -0,0 +1,15 @@
+class CNN
+  attr_reader :webpage, :headlines
+
+  CNN_US_HEADLINES_URL = "https://www.cnn.com/us"
+
+  def initialize
+    @webpage = Buzzwords::MECH.get(CNN_US_HEADLINES_URL)
+  end
+
+  def headlines
+    webpage.search('.cd__headline-text').map do |headline|
+      headline.text.downcase.strip
+    end.slice(0, 25)
+  end
+end

data/lib/buzzwords/ny_times.rb

@@ -0,0 +1,15 @@
+class NYTimes
+  attr_reader :webpage, :headlines
+
+  US_HEADLINE_URL = "https://www.nytimes.com/section/us"
+
+  def initialize
+    @webpage = Buzzwords::MECH.get(US_HEADLINE_URL)
+  end
+
+  def headlines
+    webpage.search('.initial-set .headline').map do |headline|
+      headline.text.downcase.strip
+    end
+  end
+end

data/lib/buzzwords/reuters.rb

@@ -0,0 +1,15 @@
+class Reuters
+  attr_reader :webpage, :headlines
+
+  US_HEADLINE_URL = "https://www.reuters.com/news/us"
+
+  def initialize
+    @webpage = Buzzwords::MECH.get(US_HEADLINE_URL)
+  end
+
+  def headlines
+    webpage.search('.FeedItemHeadline_full a').map do |headline|
+      headline.text.downcase.strip
+    end
+  end
+end

data/lib/buzzwords/stopwords.rb

@@ -0,0 +1,59 @@
+# https://github.com/brez/stopwords
+# Copyright ©2011 John Bresnik
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation
+# files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy,
+# modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software
+# is furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+module Stopwords
+
+  STOP_WORDS = [
+    'a', 'am', 'cannot','into','our','thus','about','co','is','ours','to','above',
+    'could','it','ourselves','together','across','down','its','out','too',
+    'after','during','itself','over','toward','afterwards','each','last','own',
+    'towards','again','eg','latter','per','under','against','either','latterly',
+    'perhaps','until','all','else','least','rather','up','almost','elsewhere',
+    'less','same','upon','alone','enough','ltd','seem','us','along','etc',
+    'many','seemed','very','already','even','may','seeming','via','also','ever',
+    'me','seems','was','although','every','meanwhile','several','we','always',
+    'everyone','might','she','well','among','everything','more','should','were',
+    'amongst','everywhere','moreover','since','what','an','except','most','so',
+    'whatever','and','few','mostly','some','when','another','first','much',
+    'somehow','whence','any','for','must','someone','whenever','anyhow',
+    'former','my','something','where','anyone','formerly','myself','sometime',
+    'whereafter','anything','from','namely','sometimes','whereas','anywhere',
+    'further','neither','somewhere','whereby','are','had','never','still',
+    'wherein','around','has','nevertheless','such','whereupon','as','have',
+    'next','than','wherever','at','he','no','that','whether','be','hence',
+    'nobody','the','whither','became','her','none','their','which','because',
+    'here','noone','them','while','become','hereafter','nor','themselves','who',
+    'becomes','hereby','not','then','whoever','becoming','herein','nothing',
+    'thence','whole','been','hereupon','now','there','whom','before','hers',
+    'nowhere','thereafter','whose','beforehand','herself','of','thereby','why',
+    'behind','him','off','therefore','will','being','himself','often','therein',
+    'with','below','his','on','thereupon','within','beside','how','once',
+    'these','without','besides','however','one','they','would','between','i',
+    'only','this','yet','beyond','ie','onto','those','you','both','if','or',
+    'though','your','but','in','other','through','yours','by','inc','others',
+    'throughout','yourself','can','indeed','otherwise','thru','yourselves', 'says',
+    'new', 'shows', 'man', 'woman', 'got', 'see', 'people'
+    ]
+  TOKEN_REGEXP = /^[a-z]+$|^\w+\-\w+|^[a-z]+[0-9]+[a-z]+$|^[0-9]+[a-z]+|^[a-z]+[0-9]+$/
+
+  def self.is?(token)
+    STOP_WORDS.member?(token)
+  end
+
+  def self.valid?(token)
+    (((token =~ TOKEN_REGEXP) == 0)) and !(STOP_WORDS.member?(token))
+  end
+
+end

data/lib/buzzwords/washington_post.rb

@@ -0,0 +1,15 @@
+class WashingtonPost
+  attr_reader :webpage, :headlines
+
+  WAPO_URL = "https://www.washingtonpost.com"
+
+  def initialize
+    @webpage = Buzzwords::MECH.get(WAPO_URL)
+  end
+
+  def headlines
+    webpage.search('#main-content .headline a').map do |headline|
+      headline.text.downcase.strip
+    end
+  end
+end

data/spec/buzzwords_spec.rb

@@ -0,0 +1,116 @@
+require 'buzzwords'
+
+describe 'buzzwords' do
+  context '.display_loading' do
+    it 'displays load message' do
+      expect { Buzzwords.display_loading }.to output(/Loading current buzzwords...\n/).to_stdout
+    end
+  end
+
+  context 'retrieve headlines' do
+    before(:each) { Buzzwords.aggregate_headlines = [] }
+
+    context '.retrieve_nytimes_headlines' do
+      it 'adds NYT headlines to aggregate' do
+        Buzzwords.retrieve_nytimes_headlines
+        expect(Buzzwords.aggregate_headlines).not_to be_empty
+      end
+    end
+
+    context '.retrieve_wapo_headlines' do
+      it 'adds Wapo headlines to aggregate' do
+        Buzzwords.retrieve_wapo_headlines
+        expect(Buzzwords.aggregate_headlines).not_to be_empty
+      end
+    end
+
+    context '.retrieve_cnn_headlines' do
+      it 'adds CNN headlines to aggregate' do
+        Buzzwords.retrieve_cnn_headlines
+        expect(Buzzwords.aggregate_headlines).not_to be_empty
+      end
+    end
+
+    context '.retrieve_reuters_headlines' do
+      it 'adds Reuters headlines to aggregate' do
+        Buzzwords.retrieve_reuters_headlines
+        expect(Buzzwords.aggregate_headlines).not_to be_empty
+      end
+    end
+  end
+
+  context '.parse_headlines' do
+    before(:all) { @headlines = Buzzwords.parse_headlines(NYTimes.new.headlines) }
+
+    it 'should return an array' do
+      expect(@headlines).to be_an_instance_of(Array)
+    end
+
+    it 'should only include properly formatted words' do
+      @headlines.each do |headline|
+        expect(headline).not_to include('/(\A[\W]||[\W]\z)/')
+        expect(headline).not_to include('/\'s/')
+      end
+    end
+  end
+
+  context '.filter_stopwords' do
+    before { Buzzwords.retrieve_nytimes_headlines }
+
+    it 'should filter stopwords from aggregate headline list' do
+      Buzzwords.filter_stopwords
+      expect(Buzzwords.aggregate_headlines).not_to include(*Stopwords::STOP_WORDS)
+    end
+  end
+
+  context '.count_word_occurrences' do
+    before(:all) do
+      Buzzwords.retrieve_cnn_headlines
+      Buzzwords.count_word_occurrences
+    end
+
+    it 'should return a hash' do
+      expect(Buzzwords.word_occurrences).to be_an_instance_of(Hash)
+      expect(Buzzwords.word_occurrences).not_to be_empty
+    end
+
+    it 'should have integer values in the hash' do
+      expect(Buzzwords.word_occurrences.values).to all(be_an(Integer))
+    end
+  end
+
+  context '.determine_top_words' do
+    before(:all) do
+      Buzzwords.retrieve_nytimes_headlines
+      Buzzwords.retrieve_cnn_headlines
+      Buzzwords.retrieve_reuters_headlines
+      Buzzwords.retrieve_wapo_headlines
+      Buzzwords.filter_stopwords
+      Buzzwords.count_word_occurrences
+      @top_words = Buzzwords.determine_top_words
+    end
+
+    it 'should return a non-empty array' do
+      expect(@top_words).to be_an_instance_of(Array)
+    end
+
+    it 'should return less than 21 words' do
+      expect(@top_words.length).to be <= 20
+    end
+
+    it 'should return list of unique words' do
+      expect(@top_words.uniq).to match(@top_words)
+    end
+  end
+
+  context '.display_top_words' do
+    it 'displays title heading' do
+      expect { Buzzwords.display_top_words }.to output(/Today's top buzzwords are: \n/).to_stdout
+    end
+
+    it 'displays list of words' do
+      Buzzwords.top_words = ['hello', 'hi', 'yes']
+      expect { Buzzwords.display_top_words }.to output(/ - hello\n - hi\n - yes\n/).to_stdout
+    end
+  end
+end

data/spec/cnn_spec.rb

@@ -0,0 +1,11 @@
+require './lib/buzzwords/cnn.rb'
+
+describe 'cnn' do
+  context '#headlines' do
+    it 'returns a non-empty array' do
+      headlines = CNN.new.headlines
+      expect(headlines).not_to be_empty
+      expect(headlines).to be_an_instance_of(Array)
+    end
+  end
+end

data/spec/ny_times_spec.rb

@@ -0,0 +1,11 @@
+require './lib/buzzwords/ny_times.rb'
+
+describe 'NY Times' do
+  context '#headlines' do
+    it 'returns a non-empty array' do
+      headlines = NYTimes.new.headlines
+      expect(headlines).not_to be_empty
+      expect(headlines).to be_an_instance_of(Array)
+    end
+  end
+end

data/spec/reuters_spec.rb

@@ -0,0 +1,11 @@
+require './lib/buzzwords/reuters.rb'
+
+describe 'Reuters' do
+  context '#headlines' do
+    it 'returns a non-empty array' do
+      headlines = Reuters.new.headlines
+      expect(headlines).not_to be_empty
+      expect(headlines).to be_an_instance_of(Array)
+    end
+  end
+end

data/spec/washington_post_spec.rb

@@ -0,0 +1,11 @@
+require './lib/buzzwords/washington_post.rb'
+
+describe 'Washington Post' do
+  context '#headlines' do
+    it 'returns a non-empty array' do
+      headlines = WashingtonPost.new.headlines
+      expect(headlines).not_to be_empty
+      expect(headlines).to be_an_instance_of(Array)
+    end
+  end
+end

metadata

@@ -0,0 +1,95 @@
+--- !ruby/object:Gem::Specification
+name: buzzwords
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Elizabeth Tackett
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-10-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.7'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.7.6
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.8'
+description: A simple IRB tool that generates and displays the day's most popular
+  buzzwords from news publications including The New York Times, The Washington Post,
+  CNN, and Reuters.
+email: emctackett@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/buzzwords.rb
+- lib/buzzwords/cnn.rb
+- lib/buzzwords/ny_times.rb
+- lib/buzzwords/reuters.rb
+- lib/buzzwords/stopwords.rb
+- lib/buzzwords/washington_post.rb
+- spec/buzzwords_spec.rb
+- spec/cnn_spec.rb
+- spec/ny_times_spec.rb
+- spec/reuters_spec.rb
+- spec/washington_post_spec.rb
+homepage: http://github.com/emctackett
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: 2.4.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.13
+signing_key: 
+specification_version: 4
+summary: A basic IRB tool to instantly generate the day's media buzzwords.
+test_files:
+- spec/buzzwords_spec.rb
+- spec/cnn_spec.rb
+- spec/ny_times_spec.rb
+- spec/reuters_spec.rb
+- spec/washington_post_spec.rb